Back-propagation algorithm based on enlarging error signals

Computer Engineering and Applications ›› 2007, Vol. 43 ›› Issue (21): 90-92.

• 学术探讨 • Previous Articles Next Articles

Back-propagation algorithm based on enlarging error signals

LIU Jia-lu，LIU Qiong-sun，HU Shang-wei

College of Science，Chongqing University，Chongqing 400030，China

Received:1900-01-01 Revised:1900-01-01 Online:2007-07-21 Published:2007-07-21
Contact: LIU Jia-lu

基于放大误差信号的BP算法

刘佳璐，刘琼荪，胡上尉

重庆大学数理学院，重庆 400030

通讯作者: 刘佳璐

Abstract

Abstract: This paper presents an improved back-propagation algorithm based on enlarging error signals.A modified derivative of the activation function is proposed to amplify the range of weight adjusting by enlarging error signals.The proposed algorithm speeds up the convergence rate by avoiding getting trapped the premature saturation.Simulation results show that the proposed algorithm always outperforms the standard back-propagation algorithms and other traditional methods in the convergence rate.

Key words: feed-forward neural network, Back-Propagation algorithm, error signal, flat spot

摘要： 提出了一种基于放大误差信号的改进BP算法，构造了一个新的函数修改激励函数的导数，通过放大误差信号，加大网络权值调整力度，避免BP算法易于陷入饱和区域来加快收敛速度。仿真结果表明，该算法在收敛速度等方面大大优于其他一些算法。

关键词: 前馈神经网络, BP算法, 误差信号, 饱和区域

LIU Jia-lu，LIU Qiong-sun，HU Shang-wei. Back-propagation algorithm based on enlarging error signals[J]. Computer Engineering and Applications, 2007, 43(21): 90-92.

刘佳璐，刘琼荪，胡上尉. 基于放大误差信号的BP算法[J]. 计算机工程与应用, 2007, 43(21): 90-92.

[1]	BU Fanyu1，2, CHEN Zhikui1, ZHANG Qingchen1. Incremental updating method for big data feature learning [J]. Computer Engineering and Applications, 2015, 51(12): 21-26.
[2]	ZHANG Yunong1，2, LAO Wenchao1, YU Xiaotian1, LI Jun1. Weights and structure determination of two-input power-activation feed-forward neural network [J]. Computer Engineering and Applications, 2012, 48(15): 102-106.
[3]	SUN Bin^1，2，LI Tieke^1，2，WANG Bailin^1，2. Neural network forecasting model based on stock market sensitivity analysis [J]. Computer Engineering and Applications, 2011, 47(1): 26-31.
[4]	TANG Yun-lan^1，2，GAO Yan-fang¹，TAN Xu¹，CHEN Ying-wu¹. Research on structure of multi-layer feed-forward neural network with cross connections [J]. Computer Engineering and Applications, 2009, 45(32): 45-47.
[5]	ZHANG Yu-dong¹,WU Le-nan¹,WU Han-qian². Comparison of neural network and evolutionary algorithm on engineering optimization [J]. Computer Engineering and Applications, 2009, 45(3): 1-6.
[6]	LI Wei-qiang，XU Jian-cheng，YIN Jian-feng. ee colony optimization algorithm for training feed-forward neural networks [J]. Computer Engineering and Applications, 2009, 45(24): 43-45.
[7]	SUN Wei-wei,LIU Qiong-sun. Joint-optimization algorithm of BP neural network [J]. Computer Engineering and Applications, 2009, 45(12): 50-51.

Back-propagation algorithm based on enlarging error signals

基于放大误差信号的BP算法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 7

Recommended Articles

Metrics